CN115187932A - Road congestion analysis system based on artificial intelligence - Google Patents

Road congestion analysis system based on artificial intelligence Download PDF

Info

Publication number
CN115187932A
CN115187932A CN202210515902.3A CN202210515902A CN115187932A CN 115187932 A CN115187932 A CN 115187932A CN 202210515902 A CN202210515902 A CN 202210515902A CN 115187932 A CN115187932 A CN 115187932A
Authority
CN
China
Prior art keywords
congestion
road
module
lane
speed
Prior art date
Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
Pending
Application number
CN202210515902.3A
Other languages
Chinese (zh)
Inventor
卢青松
杨有丽
汪培泉
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Anhui Chaoqing Technology Co ltd
Original Assignee
Anhui Chaoqing Technology Co ltd
Priority date (The priority date is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the date listed.)
Filing date
Publication date
Application filed by Anhui Chaoqing Technology Co ltd filed Critical Anhui Chaoqing Technology Co ltd
Priority to CN202210515902.3A priority Critical patent/CN115187932A/en
Publication of CN115187932A publication Critical patent/CN115187932A/en
Pending legal-status Critical Current

Links

Images

Classifications

    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
    • G06V20/00—Scenes; Scene-specific elements
    • G06V20/50—Context or environment of the image
    • G06V20/52—Surveillance or monitoring of activities, e.g. for recognising suspicious objects
    • G06V20/54—Surveillance or monitoring of activities, e.g. for recognising suspicious objects of traffic, e.g. cars on the road, trains or boats
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
    • G06V10/00—Arrangements for image or video recognition or understanding
    • G06V10/20—Image preprocessing
    • G06V10/25—Determination of region of interest [ROI] or a volume of interest [VOI]
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
    • G06V10/00—Arrangements for image or video recognition or understanding
    • G06V10/40—Extraction of image or video features
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
    • G06V10/00—Arrangements for image or video recognition or understanding
    • G06V10/70—Arrangements for image or video recognition or understanding using pattern recognition or machine learning
    • G06V10/762—Arrangements for image or video recognition or understanding using pattern recognition or machine learning using clustering, e.g. of similar faces in social networks
    • G06V10/763—Non-hierarchical techniques, e.g. based on statistics of modelling distributions
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
    • G06V10/00—Arrangements for image or video recognition or understanding
    • G06V10/70—Arrangements for image or video recognition or understanding using pattern recognition or machine learning
    • G06V10/82—Arrangements for image or video recognition or understanding using pattern recognition or machine learning using neural networks
    • G—PHYSICS
    • G08—SIGNALLING
    • G08G—TRAFFIC CONTROL SYSTEMS
    • G08G1/00—Traffic control systems for road vehicles
    • G08G1/01—Detecting movement of traffic to be counted or controlled
    • G08G1/0104—Measuring and analyzing of parameters relative to traffic conditions
    • G08G1/0125—Traffic data processing
    • G—PHYSICS
    • G08—SIGNALLING
    • G08G—TRAFFIC CONTROL SYSTEMS
    • G08G1/00—Traffic control systems for road vehicles
    • G08G1/065—Traffic control systems for road vehicles by counting the vehicles in a section of the road or in a parking area, i.e. comparing incoming count with outgoing count

Landscapes

  • Engineering & Computer Science (AREA)
  • Physics & Mathematics (AREA)
  • General Physics & Mathematics (AREA)
  • Theoretical Computer Science (AREA)
  • Multimedia (AREA)
  • Evolutionary Computation (AREA)
  • Software Systems (AREA)
  • Health & Medical Sciences (AREA)
  • Artificial Intelligence (AREA)
  • Computer Vision & Pattern Recognition (AREA)
  • Computing Systems (AREA)
  • Databases & Information Systems (AREA)
  • General Health & Medical Sciences (AREA)
  • Medical Informatics (AREA)
  • Chemical & Material Sciences (AREA)
  • Analytical Chemistry (AREA)
  • Probability & Statistics with Applications (AREA)
  • Traffic Control Systems (AREA)

Abstract

The invention relates to road congestion analysis, in particular to a road congestion analysis system based on artificial intelligence, which comprises a server, wherein the server acquires road images through a lane image acquisition module and processes the road images through a lane image processing module, the server detects vehicles in the processed road images through a target vehicle detection module and outputs the vehicle density of each lane through a vehicle density output module, and the server counts the road traffic flow according to the vehicle density of each lane through a traffic flow counting module; the technical scheme provided by the invention can effectively overcome the defects that the traffic flow of the road cannot be accurately counted and the road congestion reason cannot be effectively analyzed in the prior art.

Description

Road congestion analysis system based on artificial intelligence
Technical Field
The invention relates to road congestion analysis, in particular to a road congestion analysis system based on artificial intelligence.
Background
Artificial intelligence is a branch of computer science that attempts to understand the essence of intelligence and create a new intelligent machine that can react in a manner similar to human intelligence, and research in this field includes robotics, speech recognition, image recognition, natural language processing, and expert systems. Since the birth of artificial intelligence, theories and technologies are mature day by day, and application fields are expanded continuously.
Traffic is the life pulse of urban economic activities, and plays an important role in developing urban economy and improving the living standard of people. With the continuous development of social economy, automobiles become indispensable transportation tools for people to go out, but with the continuous increase of the ownership of automobiles, the urban traffic congestion phenomenon is increasingly serious, and great influence is brought to people to go out. The road expansion speed can not meet the normal running requirement of the motor vehicle far, so that the road congestion becomes a new normal state.
The existing road congestion analysis system cannot accurately count the traffic flow of the road and effectively analyze the reason of the road congestion, so that the management efficiency of the road congestion is low, and the problem of the road congestion cannot be fundamentally solved all the time.
Disclosure of Invention
Technical problem to be solved
Aiming at the defects in the prior art, the invention provides a road congestion analysis system based on artificial intelligence, which can effectively overcome the defects that the road traffic flow cannot be accurately counted and the road congestion cause cannot be effectively analyzed in the prior art.
(II) technical scheme
In order to achieve the purpose, the invention is realized by the following technical scheme:
a road congestion analysis system based on artificial intelligence comprises a server, wherein the server acquires road images through a lane image acquisition module and performs image processing on the road images through a lane image processing module, the server performs vehicle detection in the processed road images through a target vehicle detection module and outputs the vehicle density of each lane through a vehicle density output module, and the server performs statistics on road traffic flow according to the vehicle density of each lane through a traffic flow statistics module;
the server acquires traffic data through a traffic data acquisition module and judges congestion types through a congestion type judgment module, the server constructs a road speed space-time diagram through a speed space-time diagram construction module and extracts congestion subsets from the road speed space-time diagram through a congestion subset extraction module, the server extracts feature vectors of the congestion subsets through a feature vector extraction module and clusters the congestion subsets on the basis of the feature vectors through a congestion subset classification module, and the server analyzes congestion reasons through a congestion reason analysis module according to the congestion types and the congestion subset clustering results.
Preferably, the lane image processing module performs lane division processing on the road image, and sets an area of interest in each lane area.
Preferably, the lane image processing module traces the edge of the region of interest in one of a square, a circle, an ellipse, and an irregular polygon in the lane-divided processed image.
Preferably, the target vehicle detection module adopts a full convolution network model to perform feature extraction on the region of interest to obtain a vehicle target in the current road image;
and the vehicle density output module acquires the vehicle density of each lane by adopting a deconvolution network model.
Preferably, the traffic flow statistics module is configured to count the traffic flow of the road according to the vehicle density of each lane, and includes:
s1, calculating the number of vehicles in each lane:
Figure BDA0003641420770000021
wherein i is a lane mark number, ρ is the vehicle density of the lane, and S is the area of the region of interest in the lane region;
s2, calculating the number of vehicles in all lanes in the monitored area:
Figure BDA0003641420770000031
s3, calculating the road traffic flow in the monitoring area:
T＝v*Q/L
wherein v is the average speed of all vehicles in the monitored area, and L is the actual length of the lane in the monitored area.
Preferably, after the traffic flow statistics module performs statistics on the traffic flow of the road according to the vehicle density of each lane, the traffic flow statistics module sends the traffic flow of the road and the average speed of the vehicle to the traffic data acquisition module, and the congestion type judgment module constructs a congestion type judgment model based on the traffic flow of the road and the average speed of the vehicle:
s1, establishing a traffic flow model based on a potential function, wherein the potential function is as follows:
E＝av 4 +bQv 2
wherein a and b are undetermined coefficients;
s2, translating and rotating the coordinates of the road traffic flow and the average speed of the vehicle;
and S3, solving parameters in the sudden change manifold by using the transformed coordinate data, and obtaining a specific bifurcation set equation.
Preferably, the congestion type determining module distinguishes between frequent congestion and occasional congestion by determining whether the road traffic flow crosses a projection area crossing the bifurcation set.
Preferably, the speed space-time diagram construction module constructs a road speed space-time diagram by using average speed of vehicles on a road segment, the congestion subset extraction module extracts congestion subsets from the road speed space-time diagram through image morphological processing, the feature vector extraction module constructs a feature vector extraction model to extract feature vectors of the congestion subsets, and the congestion subset classification module performs clustering on the congestion subsets through a K-means clustering algorithm based on similar distances among the feature vectors.
Preferably, the speed space-time diagram construction module considers the propagation influence of free flow and congestion flow by constructing a dual-core function, solves the problems of data abnormality and data loss, and realizes speed smoothing and filling of the road speed space-time diagram based on a mean value interpolation method.
Preferably, the feature vector of the congestion subset comprises a speed feature and a boundary feature, the speed feature comprises a vehicle average speed, a speed standard deviation, a maximum speed and a minimum speed, and the boundary feature comprises a congestion subset edge contour and a congestion starting point.
(III) advantageous effects
Compared with the prior art, the road congestion analysis system based on artificial intelligence provided by the invention has the following beneficial effects:
1) The lane image processing module carries out lane-dividing processing on the road image, an interested area is arranged in each lane area, the target vehicle detection module adopts a full convolution network model to carry out feature extraction on the interested area to obtain a vehicle target in the current road image, the vehicle density output module adopts a deconvolution network model to obtain the vehicle density of each lane, the traffic flow counting module counts the road traffic flow according to the vehicle density of each lane, and accurate counting of the road traffic flow is realized by accurately collecting the vehicle density of each lane;
2) The congestion type judgment module judges congestion types, the speed space-time diagram construction module constructs a road speed space-time diagram, the congestion subset extraction module extracts congestion subsets from the road speed space-time diagram, the feature vector extraction module extracts feature vectors of the congestion subsets, and the congestion subset classification module clusters the congestion subsets based on the feature vectors, so that the road congestion reasons can be comprehensively and accurately analyzed by combining the congestion types and the congestion subset clustering results, the management efficiency of road congestion is effectively improved, and a comprehensive analysis basis is provided for fundamentally solving the problem of road congestion.
Drawings
In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings used in the embodiments or the prior art descriptions will be briefly described below. It is obvious that the drawings in the following description are only some embodiments of the invention, and that for a person skilled in the art, other drawings can be derived from them without inventive effort.
FIG. 1 is a schematic diagram of the system of the present invention;
FIG. 2 is a schematic view of a flow chart of the present invention for counting the traffic flow of a road according to the vehicle density of each lane;
fig. 3 is a schematic flow chart of analyzing congestion causes by combining congestion types and congestion subset clustering results in the invention.
Detailed Description
In order to make the objects, technical solutions and advantages of the embodiments of the present invention clearer, the technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the drawings in the embodiments of the present invention. It is to be understood that the embodiments described are only a few embodiments of the present invention, and not all embodiments. All other embodiments, which can be obtained by a person skilled in the art without inventive step based on the embodiments of the present invention, are within the scope of protection of the present invention.
A road congestion analysis system based on artificial intelligence is disclosed, as shown in fig. 1 and fig. 2, and comprises a server, wherein the server acquires road images through a lane image acquisition module and processes the road images through a lane image processing module, the server detects vehicles in the processed road images through a target vehicle detection module and outputs vehicle density of each lane through a vehicle density output module, and the server counts road traffic flow according to the vehicle density of each lane through a traffic flow counting module.
(1) The lane image processing module carries out lane division processing on the road image and sets an interested area in each lane area. The lane image processing module traces the edge of the region of interest in one of a square, a circle, an ellipse and an irregular polygon in the lane-divided processed image.
(2) And the target vehicle detection module adopts a full convolution network model to extract the characteristics of the region of interest to obtain the vehicle target in the current road image.
(3) And the vehicle density output module acquires the vehicle density of each lane by adopting a deconvolution network model.
(4) The traffic flow statistics module is according to the vehicle density statistics road traffic flow in each lane, includes:
s1, calculating the number of vehicles in each lane:
Figure BDA0003641420770000051
wherein i is a lane mark number, ρ is the vehicle density of the lane, and S is the area of the region of interest in the lane region;
s2, calculating the number of vehicles in all lanes in the monitored area:
Figure BDA0003641420770000052
s3, calculating the road traffic flow in the monitoring area:
T＝v*Q/L
wherein v is the average speed of all vehicles in the monitored area, and L is the actual length of the lane in the monitored area.
According to the technical scheme, the lane image processing module carries out lane processing on road images, an interested area is arranged in each lane area, the target vehicle detection module adopts a full convolution network model to carry out feature extraction on the interested area to obtain a vehicle target in the current road image, the vehicle density output module adopts a deconvolution network model to obtain the vehicle density of each lane, the traffic flow counting module counts the traffic flow of the road according to the vehicle density of each lane, and accurate counting of the traffic flow of the road is realized by accurately collecting the vehicle density of each lane.
As shown in fig. 1 and 3, a server acquires traffic data through a traffic data acquisition module, and performs congestion type judgment through a congestion type judgment module, the server constructs a road speed space-time diagram through a speed space-time diagram construction module, and extracts a congestion subset from the road speed space-time diagram through a congestion subset extraction module, the server extracts a feature vector of the congestion subset through a feature vector extraction module, and clusters the congestion subset based on the feature vector through a congestion subset classification module, and the server analyzes congestion reasons according to the congestion type and the congestion subset clustering result through a congestion reason analysis module.
After the traffic flow counting module counts the traffic flow of the road according to the vehicle density of each lane, the traffic flow and the average speed of the vehicles are sent to the traffic data acquisition module, and the traffic data acquisition module sends the traffic flow and the average speed of the vehicles to the congestion type judgment module.
The congestion type judgment module constructs a congestion type judgment model based on the road traffic flow and the average vehicle speed:
s1, establishing a traffic flow model based on a potential function, wherein the potential function is as follows:
E＝av 4 +bQv 2
wherein a and b are undetermined coefficients;
s2, translating and rotating the coordinates of the road traffic flow and the average speed of the vehicle;
and S3, solving parameters in the sudden change manifold by using the transformed coordinate data, and obtaining a specific bifurcation set equation.
The congestion type judging module distinguishes frequent congestion and occasional congestion by judging whether the road traffic flow passes through the bifurcation set projection area.
The speed space-time diagram construction module constructs a road speed space-time diagram by utilizing average speed of vehicles on a road section, the congestion subset extraction module extracts congestion subsets from the road speed space-time diagram through image morphological processing, the feature vector extraction module constructs a feature vector extraction model to extract feature vectors of the congestion subsets, and the congestion subset classification module clusters the congestion subsets through a K-means clustering algorithm based on similar distances among the feature vectors.
The speed space-time diagram construction module considers the propagation influence of free flow and congestion flow by constructing a dual-core function, solves the problems of data abnormity and data loss, and realizes speed smoothing and filling of the road speed space-time diagram based on a mean value interpolation method.
The feature vector of the congestion subset comprises a speed feature and a boundary feature, the speed feature comprises a vehicle average speed, a speed standard deviation, a maximum speed and a minimum speed, and the boundary feature comprises a congestion subset edge contour and a congestion starting point.
The server comprehensively and accurately analyzes the road congestion reasons by combining congestion types (frequent congestion/occasional congestion) with the congestion cause analysis module and clustering the congestion subsets through a K-means clustering algorithm to obtain results, so that the management efficiency of the road congestion is effectively improved, and comprehensive analysis basis is provided for fundamentally solving the problem of road congestion.
The above examples are only intended to illustrate the technical solution of the present invention, but not to limit it; although the present invention has been described in detail with reference to the foregoing embodiments, it will be understood by those of ordinary skill in the art that: the technical solutions described in the foregoing embodiments may still be modified, or some technical features may be equivalently replaced; such modifications and substitutions do not depart from the spirit and scope of the corresponding technical solutions.

Claims (10)

1. The utility model provides a road congestion analytic system based on artificial intelligence which characterized in that: the system comprises a server, a lane image acquisition module, a lane image processing module, a target vehicle detection module, a vehicle density output module and a traffic flow counting module, wherein the server acquires road images through the lane image acquisition module and processes the road images through the lane image processing module;
the server acquires traffic data through a traffic data acquisition module and judges congestion types through a congestion type judgment module, the server constructs a road speed space-time diagram through a speed space-time diagram construction module and extracts congestion subsets from the road speed space-time diagram through a congestion subset extraction module, the server extracts feature vectors of the congestion subsets through a feature vector extraction module and clusters the congestion subsets on the basis of the feature vectors through a congestion subset classification module, and the server analyzes congestion reasons through a congestion reason analysis module according to the congestion types and the congestion subset clustering results.
2. The artificial intelligence based road congestion analysis system according to claim 1, wherein: the lane image processing module carries out lane division processing on the road image and sets an interested area in each lane area.
3. The artificial intelligence based road congestion analysis system according to claim 2, wherein: the lane image processing module traces the edge of the region of interest in one of a square, a circle, an ellipse and an irregular polygon in the image after lane division processing.
4. The artificial intelligence based road congestion analysis system according to claim 2, wherein: the target vehicle detection module adopts a full convolution network model to extract the characteristics of the region of interest to obtain a vehicle target in the current road image;
and the vehicle density output module acquires the vehicle density of each lane by adopting a deconvolution network model.
5. The artificial intelligence based road congestion analysis system according to claim 4, wherein: the traffic flow statistics module is according to the vehicle density statistics road traffic flow in each lane, includes:
s1, calculating the number of vehicles in each lane:
Figure FDA0003641420760000021
wherein i is a lane mark number, ρ is the vehicle density of the lane, and S is the area of the region of interest in the lane region;
s2, calculating the number of vehicles in all lanes in the monitored area:
Figure FDA0003641420760000022
s3, calculating the road traffic flow in the monitoring area:
T＝v*Q/L
wherein v is the average speed of all vehicles in the monitored area, and L is the actual length of the lane in the monitored area.
6. The artificial intelligence based road congestion analysis system according to claim 5, wherein: the traffic flow counting module counts the traffic flow of the road according to the vehicle density of each lane, and then sends the traffic flow of the road and the average speed of the vehicles to the traffic data acquisition module, and the congestion type judgment module constructs a congestion type judgment model based on the traffic flow of the road and the average speed of the vehicles:
s1, establishing a traffic flow model based on a potential function, wherein the potential function is as follows:
E＝av 4 +bQv 2
wherein a and b are undetermined coefficients;
s2, translating and rotating the coordinates of the road traffic flow and the average speed of the vehicle;
and S3, solving parameters in the sudden change manifold by using the transformed coordinate data, and obtaining a specific bifurcation set equation.
7. The artificial intelligence based road congestion analysis system according to claim 6, wherein: the congestion type judging module distinguishes frequent congestion and occasional congestion by judging whether the road traffic flow passes through a bifurcation set projection area.
8. The artificial intelligence based road congestion analysis system according to claim 1, wherein: the speed space-time diagram construction module constructs a road speed space-time diagram by utilizing average speed of vehicles on a road section, the congestion subset extraction module extracts congestion subsets from the road speed space-time diagram through image morphological processing, the feature vector extraction module constructs a feature vector extraction model to extract feature vectors of the congestion subsets, and the congestion subset classification module clusters the congestion subsets through a K-means clustering algorithm based on similar distances among the feature vectors.
9. The artificial intelligence based road congestion analysis system according to claim 8, wherein: the speed space-time diagram construction module considers the propagation influence of free flow and congestion flow by constructing a dual-core function, solves the problems of data abnormity and data loss, and realizes speed smoothing and filling of the road speed space-time diagram based on a mean value interpolation method.
10. The artificial intelligence based road congestion analysis system according to claim 8, wherein: the feature vector of the congestion subset comprises a speed feature and a boundary feature, the speed feature comprises a vehicle average speed, a speed standard deviation, a maximum speed and a minimum speed, and the boundary feature comprises a congestion subset edge profile and a congestion starting point.
CN202210515902.3A 2022-05-12 2022-05-12 Road congestion analysis system based on artificial intelligence Pending CN115187932A (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN202210515902.3A CN115187932A (en) 2022-05-12 2022-05-12 Road congestion analysis system based on artificial intelligence

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN202210515902.3A CN115187932A (en) 2022-05-12 2022-05-12 Road congestion analysis system based on artificial intelligence

Publications (1)

Publication Number Publication Date
CN115187932A true CN115187932A (en) 2022-10-14

Family

ID=83513786

Family Applications (1)

Application Number Title Priority Date Filing Date
CN202210515902.3A Pending CN115187932A (en) 2022-05-12 2022-05-12 Road congestion analysis system based on artificial intelligence

Country Status (1)

Country Link
CN (1) CN115187932A (en)

Cited By (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN116311913A (en) * 2023-02-17 2023-06-23 成都和乐信软件有限公司 High-speed road section congestion analysis method and system based on AI video intelligent analysis
CN116403411A (en) * 2023-06-08 2023-07-07 山东协和学院 Traffic jam prediction method and system based on multiple signal sources

Cited By (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN116311913A (en) * 2023-02-17 2023-06-23 成都和乐信软件有限公司 High-speed road section congestion analysis method and system based on AI video intelligent analysis
CN116311913B (en) * 2023-02-17 2024-01-12 成都和乐信软件有限公司 High-speed road section congestion analysis method and system based on AI video intelligent analysis
CN116403411A (en) * 2023-06-08 2023-07-07 山东协和学院 Traffic jam prediction method and system based on multiple signal sources
CN116403411B (en) * 2023-06-08 2023-08-11 山东协和学院 Traffic jam prediction method and system based on multiple signal sources

Similar Documents

Publication Publication Date Title
CN109829403B (en) Vehicle anti-collision early warning method and system based on deep learning
CN115187932A (en) Road congestion analysis system based on artificial intelligence
CN103235933B (en) A kind of vehicle abnormality behavioral value method based on HMM
Fu et al. Similarity based vehicle trajectory clustering and anomaly detection
CN108052880A (en) Traffic monitoring scene actual situation method for detecting lane lines
CN103839065A (en) Extraction method for dynamic crowd gathering characteristics
CN105138982A (en) Crowd abnormity detection and evaluation method based on multi-characteristic cluster and classification
CN103854027A (en) Crowd behavior identification method
Liu et al. An efficient method for high-speed railway dropper fault detection based on depthwise separable convolution
Yang et al. Improved lane detection with multilevel features in branch convolutional neural networks
CN104504377A (en) Bus passenger crowding degree identification system and method
CN107944628A (en) A kind of accumulation mode under road network environment finds method and system
CN114359876B (en) Vehicle target identification method and storage medium
CN103886609B (en) Vehicle tracking method based on particle filtering and LBP features
CN105243354B (en) A kind of vehicle checking method based on target feature point
CN111640304A (en) Automatic quantitative extraction method for traffic jam propagation characteristics of continuous flow traffic facility
Yang Research on lane recognition algorithm based on deep learning
Gad et al. Real-time lane instance segmentation using segnet and image processing
CN101216886B (en) A shot clustering method based on spectral segmentation theory
CN113516105A (en) Lane detection method and device and computer readable storage medium
Wang et al. Lane detection based on two-stage noise features filtering and clustering
CN112801181B (en) Urban signaling traffic flow user classification and prediction method, storage medium and system
CN102201060B (en) Method for tracking and evaluating nonparametric outline based on shape semanteme
CN113033363A (en) Vehicle dense target detection method based on deep learning
CN104537392A (en) Object detection method based on distinguishing semantic component learning

Legal Events

Date Code Title Description
PB01 Publication
PB01 Publication
SE01 Entry into force of request for substantive examination
SE01 Entry into force of request for substantive examination